© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 21543
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases referring to influences or relationships among entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.04
    2:0.11
    3:0.05
    4:0.18
    5:0.09
    6:0.04
    7:0.03
    8:0.09
    9:0.19
    10:0.06
    11:0.04
    Negative Logits
    Definition
    -1.35
     redu
    -1.27
    Course
    -1.23
     Priority
    -1.17
     Synd
    -1.14
    omy
    -1.14
    ova
    -1.13
    course
    -1.11
    Ey
    -1.11
     Extension
    -1.10
    POSITIVE LOGITS
     footsteps
    1.84
     adversity
    1.47
    laus
    1.43
    regor
    1.36
    agues
    1.31
    bley
    1.29
     jog
    1.25
    ��
    1.23
     heights
    1.23
     Gaul
    1.23
    Activations Density 0.002%

    No Known Activations